Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the...
-
Upload
marianna-poole -
Category
Documents
-
view
219 -
download
3
Transcript of Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the...
![Page 1: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/1.jpg)
Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain
George Chen, Evelina Fedorenko, Nancy Kanwisher, Polina Golland
12/16/2011 NIPS MLINI Workshop 2011 1
![Page 2: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/2.jpg)
Talk Outline
1. Finding correspondences between functional regions in the brain
2. A new generative model
3. Results for language fMRI study
12/16/2011 NIPS MLINI Workshop 2011 2
![Page 3: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/3.jpg)
Functional Region Correspondences
12/16/2011 NIPS MLINI Workshop 2011 3
• Given stimulus, get functional activation regions
Subject 1
Subject 2
Align to common anatomical space
Functional variability!
Goal: Find correspondences between “parcels”
contiguous region in brain
group-level parcels
Parcel: contiguous region in brain
Biology:brain compartmentalized into functional modules parcels represent these modules
![Page 4: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/4.jpg)
Functional Variability
• Standard approach: just average in common anatomical space
12/16/2011 NIPS MLINI Workshop 2011 4
Functional variability less pronounced activation in group average
space
Subject 1
Subject 2space
Averagespace
Alignedspace
![Page 5: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/5.jpg)
Previous Work
• Thirion et al. 2007: treat parcels as discrete objects and find parcel correspondences across subjects by matching
• Xu et al. 2009: generative, hierarchical model representing activation regions as Gaussian mixtures
• Sabuncu et al. 2010: groupwise functional registration
12/16/2011 NIPS MLINI Workshop 2011 5
![Page 6: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/6.jpg)
Previous Work
• Thirion et al. 2007: treat parcels as discrete objects and find parcel correspondences across subjects by matching
• Xu et al. 2009: generative, hierarchical model representing activation regions as Gaussian mixtures
• Sabuncu et al. 2010: groupwise functional registration
12/16/2011 NIPS MLINI Workshop 2011 6
![Page 7: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/7.jpg)
Our Generative Model
12/16/2011 NIPS MLINI Workshop 2011 7
To generate image for a subject:1. Choose weights for each
group-level parcel2. Form weighted sum of
group-level parcels
3. Deform pre-image and add noise
Pre-image
e.g. (0.2, 1)
𝐷1
𝐷2
𝑦 𝑛
𝑤𝑛
Deformation:
𝑛=1 ,…,𝑁
Group-level parcels
1:
2:
0.2× +1× ¿
…𝐷𝐾
𝑦 𝑛=(∑𝑘=1
𝐾
𝑤𝑛𝑘𝐷𝑘)∘Φ𝑛−1+noise
sparse, no deformations sparse coding
i.i.d. entriesi.i.d. prior
Goal: Estimate group-level parcels and deformations
![Page 8: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/8.jpg)
Estimating Group-level Parcels and Deformations
• Priors on group-level parcels and deformations–
from image registration– Want to be parcel, have sparse support, and smooth
• Want MAP estimate:
• Use generalized EM algorithm for MAP estimation
12/16/2011 NIPS MLINI Workshop 2011 8
𝑝 (𝐷𝑘 )∝ exp (−𝜉‖𝐷𝑘‖1−𝜂 𝐷𝑘𝑇𝐋𝐷𝑘 ) 𝕝 {𝐷𝑘is unimodal∧‖𝐷𝑘‖2≤1}
argmax𝐷 , Φ
𝑝 (𝐷 ,Φ|𝑦 )=argmax𝐷 ,Φ
𝑝 ( 𝑦 ,𝐷 ,Φ )
Don’t get to observe ’s!
sparsity smoothness parcel identifiability
¿ argmax𝐷 , Φ
𝑝 (𝐷 )𝑝 (Φ)∑𝑤
𝑝 (𝑦 ,𝑤|𝐷 ,Φ )
![Page 9: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/9.jpg)
Language fMRI Study
• Data– Substantial functional variability!– 33 subjects– Contrast: reading sentences vs. pronounceable
nonwords– are t-statistic images from standard fMRI preprocessing– All images initially brought into common anatomical
space
• What we’ll show– Estimated group-level parcels correspond to language
processing regions– Estimated deformations improve fMRI group analysis
12/16/2011 NIPS MLINI Workshop 2011 9
![Page 10: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/10.jpg)
• Left frontal lobe
• Left temporal lobe
Estimated Group-level Parcels
• Correspond to known language processing regions
12/16/2011 NIPS MLINI Workshop 2011 10
Spatial support of group-level parcels
• Right temporal lobe • Right cerebellum
Example group-level parcels
![Page 11: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/11.jpg)
• Apply estimated deformation to fMRI data for each subject and redo standard fMRI group analysis on separate data
12/16/2011 NIPS MLINI Workshop 2011 11
Modeling functional variability increases statistical significance in each group-level parcel
Group-level Parcel Index
Negative log p-value
Improving fMRI Group Analysis with Estimated Deformations
![Page 12: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/12.jpg)
Improving fMRI Group Analysis with Estimated Deformations
12/16/2011 NIPS MLINI Workshop 2011 12
space
Subject 1
Subject 2
Average
Alignedspace
space
space
Why is the variance so high for statistical significance values for our model?
![Page 13: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/13.jpg)
Improving fMRI Group Analysis with Estimated Deformations
12/16/2011 NIPS MLINI Workshop 2011 13
Averagespace
Why is the variance so high for statistical significance values for our model?
Group-level parcel support
Variation using anatomical
alignment only
Variation using our model
![Page 14: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/14.jpg)
• Apply estimated deformation to fMRI data for each subject and redo standard fMRI group analysis
12/16/2011 NIPS MLINI Workshop 2011 14
Modeling functional variability increases statistical significance in each group-level parcel
Group-level Parcel Index
Negative log p-value
Improving fMRI Group Analysis with Estimated Deformations
![Page 15: Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain George Chen, Evelina Fedorenko, Nancy Kanwisher,](https://reader036.fdocuments.us/reader036/viewer/2022062407/56649ccb5503460f9499525b/html5/thumbnails/15.jpg)
Contributions
• Generative model for finding group-level parcels– Represent discrete set of parcels as images– Model implicitly represents correspondences
Just look at where -th group-level parcel shows up in each subject!
– Get deformations out of model, not just parcel correspondences! Improves fMRI group analysis
• Future directions– Use estimated parcels in other fMRI studies as markers
for language processing (and other stimuli!)
12/16/2011 NIPS MLINI Workshop 2011 15